add vqa tests

ammico/test/test_image_summary.py

@@ -0,0 +1,37 @@
+from ammico.image_summary import ImageSummaryDetector
+
+import pytest
+
+
+@pytest.mark.long
+def test_image_summary_detector(model, get_testdict):
+    detector = ImageSummaryDetector(summary_model=model, subdict=get_testdict)
+    results = detector.analyse_images_from_dict(analysis_type="summary")
+    assert len(results) == 2
+    for key in get_testdict.keys():
+        assert key in results
+        assert "caption" in results[key]
+        assert isinstance(results[key]["caption"], str)
+        assert len(results[key]["caption"]) > 0
+
+
+@pytest.mark.long
+def test_image_summary_detector_questions(model, get_testdict):
+    list_of_questions = [
+        "What is happening in the image?",
+        "How many cars are in the image in total?",
+    ]
+    detector = ImageSummaryDetector(summary_model=model, subdict=get_testdict)
+    results = detector.analyse_images_from_dict(
+        analysis_type="questions", list_of_questions=list_of_questions
+    )
+    assert len(results) == 2
+    for key in get_testdict.keys():
+        assert "vqa" in results[key]
+        if key == "IMG_2746":
+            assert "marathon" in results[key]["vqa"][0].lower()
+
+        if key == "IMG_2809":
+            assert (
+                "two" in results[key]["vqa"][1].lower() or "2" in results[key]["vqa"][1]
+            )

ammico/test/test_model.py

@@ -1,8 +1,8 @@
 import pytest
-import torch
 from ammico.model import MultimodalSummaryModel
 
 
+@pytest.mark.long
 def test_model_init(model):
     assert model.model is not None
     assert model.processor is not None
@@ -10,16 +10,19 @@ def test_model_init(model):
     assert model.device is not None
 
 
+@pytest.mark.long
 def test_model_invalid_device():
     with pytest.raises(ValueError):
         MultimodalSummaryModel(device="invalid_device")
 
 
+@pytest.mark.long
 def test_model_invalid_model_id():
     with pytest.raises(ValueError):
         MultimodalSummaryModel(model_id="non_existent_model", device="cpu")
 
 
+@pytest.mark.long
 def test_free_resources():
     model = MultimodalSummaryModel(device="cpu")
     model.close()

pyproject.toml

@@ -39,7 +39,7 @@ dependencies = [
     "pandas",
     "Pillow",
     "pooch",
-    "qwen-vl-utils[decord]==0.0.8",
+    "qwen-vl-utils",
     "retina_face",
     "safetensors>=0.6.2",
     "setuptools",